C ++正则表达式行为

Question

I have check this simple regex test in regexr or regexpal : \\"[a-zA-Z_0-9-]+\\"[\\s] :[\\s] ([0-9] 1[0-9] |\\"[a-zA-Z_0-9:\\s-\\,./\\=;] 1[a-zA-Z_0-9:\\s-\\,./\\=;] \\")

text : "dataStoreMaxConns" : 100, "dataStoreName" : "cofax", "dataStorePassword" : "dataStoreTestQuery", "dataStoreTestQuery" : "SET NOCOUNT ON;select test='test';", "dataStoreUrl" : "jdbc:microsoft:sqlserver://LOCALHOST:1433;DatabaseName=goon"

Result : 2 matches

1. "dataStoreMaxConns" : 100
2. "jdbc:microsoft:sqlserver://LOCALHOST:1433;DatabaseName=goon"

I have try with c++ any in https://wandbox.org/ and vs2010 standalone:

 #include <iostream>
#include <fstream>
#include <string>
#include <regex>
#include <iterator>

//using namespace std;

int main()
{
    std::string format_1;
    std::string main,dig,phrase;
    std::ifstream infile("noname-2");
    if(infile.good()==false)
        return false;



    main="\\\"[a-zA-Z_0-9\\-]+\\\"[\\s]*:[\\s]*";
    dig="[0-9]*1[0-9]*";
    phrase="\\\"[a-zA-Z_0-9:\\s\\-\\,\\.\/\\=;]*1[a-zA-Z_0-9:\\s\\-\\,\\.\/\\=;]*\\\"";

    format_1=main+"("+dig+"|"+phrase+")";
    std::string str((std::istreambuf_iterator<char>(infile)),std::istreambuf_iterator<char>());
    std::regex f_1(format_1,std::regex_constants::icase);

    std::smatch m_1;
    for(auto it = std::sregex_iterator(str.begin(), str.end(), f_1);it != std::sregex_iterator();++it)
    {
         std::cout<<it->str()<<std::endl;
    }
   return 0;
}

nonname-2 contains the text

Result is only one: "dataStoreMaxConns" : 100

Why?

Answer 1

You need to remove unnecessary escape symbols and make sure the - symbol is placed at the start/end of the character class (when escaped, in C++ std::regex does not really handle it as a literal char).

Use

std::string main2="\"[a-zA-Z_0-9-]+\"\\s*:\\s*";
std::string dig="[0-9]*1[0-9]*";
std::string phrase="\"[a-zA-Z_0-9:\\s,./=;\\\\-]*1[a-zA-Z_0-9:\\s,./=;\\\\-]*\"";

See the C++ demo :

#include <iostream>
#include <string>
#include <regex>

int main()
{
    std::string main2="\"[a-zA-Z_0-9-]+\"\\s*:\\s*";
    std::string dig="[0-9]*1[0-9]*";
    std::string phrase="\"[a-zA-Z_0-9:\\s,./=;\\\\-]*1[a-zA-Z_0-9:\\s,./=;\\\\-]*\"";

    std::string format_1=main2+"("+dig+"|"+phrase+")";
    std::string str("\"dataStoreMaxConns\" : 100,\n\"dataStoreName\" : \"cofax\",\n\"dataStorePassword\" : \"dataStoreTestQuery\",\n\"dataStoreTestQuery\" : \"SET NOCOUNT ON;select test='test';\",\n\"dataStoreUrl\" : \"jdbc:microsoft:sqlserver://LOCALHOST:1433;DatabaseName=goon\"");
    std::regex f_1(format_1,std::regex_constants::icase);

    std::smatch m_1;
    for(auto it = std::sregex_iterator(str.begin(), str.end(), f_1);it != std::sregex_iterator();++it)
    {
         std::cout<<it->str()<<std::endl;
    }
   return 0;
}